Claude Models Guide
Learning
Notes on Claude models, agents, harnesses, context engineering and the tools around them. 7 topics, last updated .
Claude Models Guide
Start with Opus 5.5 for most work. Drop to Sonnet 5.5 or Haiku 5.5 to save cost and time, and step up to Fable 5.1 only when Opus at high effort still fails.
9 sections · 3 tables 02Browser & computer use
For most people the best setup is Claude in Chrome for anything on a website, and Claude's computer use for desktop apps, running on Opus 5.5. Developers building their own agent should…
8 sections · 5 tables 03Hermes Agent
Hermes Agent is a free, open-source AI assistant that lives on your own computer or server, remembers what it learns, and gets better at your tasks the longer you use it. Use it for…
10 sections · 2 diagrams · 7 tables 04Context Engineering
Context engineering means deciding exactly what information an AI sees at each step, not just how you word the instruction. Anthropic's rule of thumb: give the model the smallest set of…
8 sections · 2 diagrams · 5 tables 05Claude Duet
Claude Duet is one Claude that works like your personal chief of staff: you text it what you want, it does the legwork in the background, and it comes back with the answer or a draft for…
16 sections · 4 diagrams · 12 tables 06Agent Harnesses
A harness is the program wrapped around a model: its loop, tools, memory, permissions and where it runs. On Terminal-Bench the same model scores 9 to 14 points higher in a tuned harness,…
8 sections · 6 diagrams · 3 tables 07Tailscale
Tailscale puts all your devices on one private network that works from anywhere, with no ports opened and no VPN server to run.
21 sections · 9 diagrams · 18 tables